INDEX

Explanations

phrases related to the removal or elimination of something

oai_token-act-pair · gpt-3.5-turbo

concepts related to removal or elimination of entities or conditions

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

yssey

-0.67

 unfold

-0.65

urry

-0.64

 ACTIONS

-0.64

ilant

-0.64

ificent

-0.62

 unfolding

-0.61

umbn

-0.61

ifted

-0.60

 Rescue

-0.60

POSITIVE LOGITS

 altogether

1.59

 entirely

1.11

 obsolete

1.00

 inhib

0.98

 barriers

0.90

 redundant

0.90

 pesky

0.89

 imped

0.87

 veil

0.85

 prematurely

0.84

Activations Density 0.694%

phrases related to the removal or elimination of something

concepts related to removal or elimination of entities or conditions

No Comments

No Known Activations